Frequently asked questions
Answers to common questions about the Ethen platform, Gateway, model library, and documentation.
Platform
What is Ethen? Ethen is a model workspace: a single place to choose models, route requests through one API, build with them across product surfaces, and keep an evidence trail of what ran.
Who is Ethen for? Developers integrating models through the Ethen Gateway, operators running agents and workflows with approvals, and teams that need one workspace instead of many disconnected tools.
Is Ethen generally available? Product surfaces carry different maturity labels. The Ethen Gateway is in Private Alpha. The Model Library is in Beta. Other surfaces are labelled Preview, Beta, or Setup guide only. See each surface's documentation for its current maturity status.
Gateway
How does Gateway authentication work? Every Gateway API request requires an API key sent as a Bearer token in the Authorization header. Keys are hashed with SHA-256 + salt before storage. See the authentication guide.
Which providers does the Gateway support? The Gateway supports OpenAI, Anthropic, DeepSeek, and any OpenAI-compatible endpoint. Provider availability depends on configuration (environment variables or BYOK credentials).
Does the Gateway support streaming? Yes. Set "stream": true in the request body to receive responses as SSE (server-sent events). See the Gateway quickstart.
What happens when a provider is unavailable? The Gateway falls back to the next configured provider in the priority chain. Each attempt is logged with status, latency, and error details.
Models
Where can I browse available models? The Model Library is the central catalog. You can also list models through the Model Intelligence API.
How do I choose a model? Start from the task, not the model. Match the workload to the smallest model that reliably meets quality and latency needs. See the choosing a model guide.
Can I run models locally? Yes. Ethen supports local model runtimes through Ollama and LM Studio. See the local versus hosted models guide.
Documentation
This FAQ content is placeholder. The questions above are derived from observed product surfaces and common integration patterns. They do not constitute official product guidance. Review with product ownership before publication.